NCI’s Division of Cancer Biology Supports Diverse Cancer Data Science That Uses Machine Learning and Artificial Intelligence

NCI supports the application of data science within cancer research through grant funding. NCI’s Division of Cancer Biology (DCB) research grantees recently published data science content related to machine learning and artificial intelligence. These research results hold clues to how we research and develop various cancer treatments.

Machine Learning (ML)

  • Atlas of clinically distinct cell states and ecosystems across human solid tumors,” Cell
    • Program: Cancer Systems Biology Consortium (CSBC)
    • Program Director: Shannon Hughes, Ph.D.
    • NIH Grant Numbers: U54CA209971, R01CA255450, R00CA187192, and U24CA224309, R01CA233975, R01CA229529
    • Description: This paper introduces EcoTyper, an ML framework that enables the generation of an atlas of cell states and ecosystems across tumors. Using EcoTyper for characterizing cell states and multicellular communities from gene expression data showed that different tumor ecosystems have specific cancer biology and clinical response. These findings could help produce more targeted cancer therapies.
  • Unsupervised machine learning reveals key immune cell subsets in COVID-19, rhinovirus infection, and cancer therapy,” eLife
    • Program: CSBC
    • Program Director: Shannon Hughes, Ph.D.
    • NIH Grant Numbers:  U54CA217450, U01AI25056, R01CA226833, T32AI007496, R21AI138077, U01TR002625
    • Description: The ML workflow Tracking Responders EXpanding (T-REX) was created to identify changes in both rare and common cells across human immune monitoring settings. In analyzing two data sets, T-REX identified modest, large, and extensive changes in both melanoma and acute myeloid leukemia patients.

Data Exploration

  • Interpretation of cancer mutations using a multiscale map of proteins,Science
    • Program: CSBC
    • Program Director: Shannon Hughes, Ph.D.
    • NIH Grant Number(s): U54CA209891, U54CA209988, F99CA212456, R01GM132322, S10 OD026929, F30CA236404, R50 CA243885, R01HG00997, F32CA239336, R01DE026870, P41GM103504
    • Description: CSBC investigators used proteomic mass spectrometry and data integration to build a structured map of protein assemblies in human cancer cells. They identified NeST systems that serve as biomarkers of cancer outcomes.

To keep up on more data science content like this, visit the DCB website and follow them on Twitter.

Vote below about this page’s helpfulness.